Damage Detection Based on ESPI and SVM

Long Liu; Guang Meng; Hai Huang

doi:10.4028/www.scientific.net/KEM.324-325.1309

Paper Titles

Discrete-Continuous Configuration Optimization Methods for Structures Using the Harmony Search Algorithm
p.1293

Synthesis and Characterization of the ZnO-TiO₂ Nanoparticles by a Hydrothermal Processing
p.1297

Optimization Conditions of Spot Welding Using Genetic Algorithm
p.1301

A Bi-Material Wedge – a Model for the Prediction of Failure Initiation at Shape and Material Discontinuities
p.1305

Damage Detection Based on ESPI and SVM
p.1309

Punching Shear Strength Considering Cumulative Damage for FRP Strengthened Bridge Decks under Fatigue Loading
p.1313

Quasi-Brittle Fracture of Lamellar γTiAl: Simulation Using a Cohesive Model with Stochastic Approach
p.1317

Fatigue Threshold of Nitrided and Shot Peened Specimens
p.1321

Analysis of Premature Rip-Off Failure Mechanism of Reinforced Concrete Beams Strengthened with FRPs
p.1325

HomeKey Engineering MaterialsKey Engineering Materials Vols. 324-325Damage Detection Based on ESPI and SVM

Damage Detection Based on ESPI and SVM

Abstract:

An approach of damage detection based on ESPI and SVM is proposed. ESPI (Electronic Speckle Pattern Interferometry) is a non-contacting measuring method, which can measure the small static and dynamitic surface deformations and reveal the flaws by looking for flaw-induced deformation anomalies. Support Vector Machine (SVM) is a machine learning algorithm based on statistical learning theory, and it has recently been established as a powerful tool for classification and regression problems. To develop the precision of processing the pattern fringe data, the SVM is introduced to process the patterns corrupted by the laser speckle effect. The SVM is trained with fringe patterns generated from a finite element model and a simple model of the laser speckle effect. The output pattern is obtained to flag whether the damage exists or not. The trained SVM is tested for robustness with model generated test patterns of a flat plate. The results show that this approach is a promising and effective for damage detection.